change figure names

5d66f644 · Mara Lampert · GitHub · cd754c37 · 5d66f644 · 5d66f644
Unverified Commit 5d66f644 authored 2 years ago by Mara Lampert Committed by GitHub 2 years ago
--- a/plots/Figure 5.06_small_label_exclusion.ipynb
+++ b/plots/Figure 5.06_small_label_exclusion.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "15fee2ed-980b-4d1a-a31a-1e261c31d9aa",
+   "metadata": {},
+   "source": [
+    "# Figure 5.06: Small label exclusion"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "39cd2c59-0e87-4083-8158-c8b4307a7126",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "import matplotlib as mpl\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "3dcc5326-9284-4da5-90eb-69ae42bb4ad6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "all_labels_training = pd.read_csv(\"Measurements_with_frame_clustering_with_GMM.csv\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "0abc6b00-0cec-4a92-a30c-d97ae5094af2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "area = all_labels_training['area_norm']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "aa69fed7-a1f4-48df-9f8e-31a5207dbfb8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "threshold = 50"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "1284e287-6ac8-4cf6-93cf-7fa8eeed6fd0",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'Distribution of labels before small label exclusion')"
+      ]
+     },
+     "execution_count": 34,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY4AAAEWCAYAAABxMXBSAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/YYfK9AAAACXBIWXMAAAsTAAALEwEAmpwYAAAmhUlEQVR4nO3de5xVVf3/8dcbGhwviBcUkTHAohBxHAmRhK9KWpppmGliGpia37Sbv0xDzTK/0o/8mdnX0kItsJJLJmr+fvXVUET8ZoA6EqIoBMgIcktRVBTm+/n9sfcMh5kzzNkzc+bivJ+Px3mcfdZee+111rl8zlp7n7UVEZiZmRWqS1tXwMzMOhYHDjMzy8SBw8zMMnHgMDOzTBw4zMwsEwcOMzPLxIEjI0m/lHRNC5X1QUmbJXVNH8+WdGFLlJ2W92dJ41qqvAz7vV7SBkmv5ll3nKSqAss5T9LcJtahSds25zWQ1EvSHElvSvpJU8pobyRNlnR9urzT105SSPpwAWX2S/N+oAn1afK2TdGc92CdcjZLOrgl6tQetErjdxSSVgC9gG1ANbAYuAuYFBH/AxARX81Q1oUR8deG8kTEy8Aezat17f6uBT4cEefmlP/plig7Yz0OAi4D+kbEutbefxu7CNgA7Bn+g5TliIgW+Zy3F+5x1HdqRHQH+gITge8Cd7b0TlrrF1Mb6Ats7IRBA5LnvrgpQeN9/H6w9yEHjgZExKaIeAA4CxgnaTDU67r3lPSgpNcl/UvS45K6SPot8EHgT2kX9YqcLvYFkl4GHmmg2/0hSfMkbZJ0v6R90n3VGyaQtELSCZJOAq4Czkr392y6vnbYJa3X9yStlLRO0l2SeqTrauoxTtLL6TDT1Q21jaQe6fbr0/K+l5Z/AvAwcGBaj8mNtbOk8ZKWpcM7iyV9rn4W3ZK2xwuSjq9TjzslrZH0SjpE1jXPPiTpp+nz3iRpYc3r2YC8r0Fa1nBJ/52+5s9KOi5NnwyMA65In/sJknaRdLOk1entZkm7pPmPk1Ql6btKhvR+k7ZhTXtslDQjd991nlPe9166boWky9Pn+VbaRr2UDF2+KemvkvbOKesPkl5Nn+8cSYfu/FVrnKTPSHpG0huSVinpEdd1ftouayRdlrNtwe2QZ78HSvpj+t5cLumbafo+aXufmj7eQ9JSSWPTxwdJujfdbqOkn+cpu97nVTt+xj4s6bG0HTdImp6Tr3YYTw18ftJ150maK+lGSa+lz6HVRw4a48DRiIiYB1QB/5Zn9WXpuv1IhriuSjaJLwEvk/Re9oiIG3K2ORY4BDixgV2OBc4HDiQZMvvPAur4F+BHwPR0f4fnyXZeehsFHEwyRFb3wzES+ChwPPB9SYc0sMtbgB5pOcemdf5yOiz3aWB1Wo/zGqs7sIykbXsAPwR+J6l3zvqjgH8CPYEfAPfmfIlMIWmjDwNHAJ8C8h2f+BRwDPARYC+SHwMbd1KnvK+BpD7A/wWuB/YBvgP8UdJ+6XP9PXBD+tz/ClwNDAcqgMOBYcD3cvZzQFpOX5Jhrm8Cp5G06YHAa8AvGqhj3vdezvrPA59Mn/OpwJ/TPD1JPvffzMn7Z2AAsD/wdPo8mustknbcC/gMcLGk0+rkGZXu91PAeCU/PCBbO9RKv3z/BDwL9CF5H18q6cSI+BfJa3q7pP2BnwKVEXGXkh8bDwIrgX7pttOa8Jz/A3gI2BsoI/mc5JP385Oz/ihgCclrdQNwpyQ1oT7FExG+pTdgBXBCnvQngavT5cnA9enydcD9JMcWdloWyRsygIPzpH0gfTwbmJizfhDwHtAVOA6oamgfwLXA7+qsn01ynAVgFnBJzrqPAltJjnPV1KMsZ/08YEye59UVeBcYlJP278DsdLlePets39j6SmB0unwesBpQnXp9ieTL8l1g15x1ZwOP5mw7N13+BPAiyZd4l0beAzt7Db4L/LZO/v8CxtV9b6SPlwEn5zw+EViR0w7vAaU5658Hjs953LvmNcpTz8bee+fkPP4jcFvO428A9zXw/PdK3ws98rzfG3vtIl990nU3Az+t874fmLP+BuDOxtqBOp+ZOvs4Cni5TtqVwG9yHt8C/CN9X+2bpn0cWN9Ambnvo3r7ZsfP2F3AJHI+R3XbhsY/P+cBS3PW7ZZue8DO3retfXOPozB9gH/lSf8/wFLgIUn/lDS+gLJWZVi/Eigh+eXRXAem5eWW/QGSL+AauWdBvU3+A/c9gW55yurTlEpJGiupMh1yeR0YzI7P95VIP0E5+zqQ5Fd6CbAmZ9tfkfxq3kFEPELSu/oFsFbSJEl77qRaDb0GfYEza/aX7nMkyRdbPvna/MCcx+sjYkvO477AzJyynyc5SSP3NarR2Htvbc7yO3ke7wEgqaukiemw0BskQQea+Z6TdJSkR9PhmE3AV/OUWbeda9omSzvk6ksyTJr7+lxVZ7tJJO+x30RETa/zIGBlRGzL9CTruwIQME/Sc5LOz5OnkM9P7ecwIt5OF9vVwXUHjkZIOpLkRa13Sl5EvBkRl0XEwSTDAd/W9jH4hg6QNnbg9KCc5Q+S/NLaQNL13y2nXl1JhikKLXc1yQcrt+xt7PiFUogNaZ3qlvVKxnKQ1Be4Hfg6ya+/vYBFJB++Gn3qdNM/SPJcVpH8cusZEXultz0jIu/4fET8Z0R8DDiUZPjm8p1UraHXYBVJj2OvnNvuETGxgXLytfnq3GrVyb8K+HSd8ksjol7bNvLey+KLwGjgBJLhk35penOHRu4GHgAOiogewC/zlFm3nWvapuB2qGMVsLzOdt0j4mSo/cz8iqRncLG2nzq8CvigGj9B4a30frectANqFiLi1Yj4SkQcSNKLuFX1T09usc9PW3LgaICkPSWdQjLW+buI+EeePKekB8QEvEHyq6g6Xb2WZAwzq3MlDZK0G8lwxD0RUU0y1FKaHnQsIRkr3yVnu7VAv5qDbHlMBf6XpP6S9mD7MZFMv7LSuswAJkjqnn75fxv4XZZyUruTfHmuB5D0ZZJfg7n2B74pqUTSmSTHh/5fRKwhGU/+SfpadZH0IUnH1t2JpCPTX8AlJB/+LWx/nfJp6DX4HXCqpBPTX+qlSg5ylzVQzlTge5L2k9QT+D47b6dfkrRr37Te+0kanS9jI++9LLqTBOCNJF+IP2pCGQ2V+6+I2CJpGEmAqusaSbspORj/ZaDmYHLB7VDHPOANJScc7Jq+RoPTH3+Q9D4gOdZxI1BzfGMesAaYKGn39HUdUbfwiFhP8gV/blr2+cCHatZLOjPnvfAayXu7uk4ZLfn5aTMOHPX9SdKbJL9CrgZuYscDV7kGAH8FNgN/A26NiNnpuv9N8qXxuqTvZNj/b0nGlV8FSkkPYkbEJuAS4A6SN+9bJAdHa/whvd8o6ek85f46LXsOsJzky/MbGeqV6xvp/v9J0hO7Oy0/k4hYDPyEpO3WAocBT9TJ9neSdt4ATADOyBliGEvS7V9M8kG9h/zDRnuS9GxeIxkW2EjyxdGQhl6DVSS/zq8iCXarSHouDX2OrgcWAAtJxtWfTtMa8jOSX+kPpe/BJ0nG7fPZ2Xsvi7tI2uQVknZ8sgll5HMJcF36PL5P8mVZ12Mkw22zgBsj4qE0PUs71Eq/lE8lORlhOcl75g6gh6SPkXxBj03z/Zjki318znYfJjmppYrkBIp8vkLymm8k6b3+d866I4G/S9qc1v9bEbE8Txkt8vlpS9px+NjMzGzn3OMwM7NMHDjMzCwTBw4zM8vEgcPMzDLp0BOr9ezZM/r169emddi8ZAkAe3z0o21aDzOzQj311FMbImK/xnPmV9TAoWRq8TdJzmXeFhFD03mGppP80WgF8IWIeC3NfyVwQZr/mxHxXzsrv1+/fixYsKBo9S/E48eNAuDfZj/apvUwMyuUpJWN52pYawxVjYqIiogYmj4eD8yKiAEk52+PB5A0CBhDcm70SST/uqw306mZmbWttjjGMZpkVlPS+9Ny0qdFxLvpn2aWkswmamZm7UixA0eQ/PvzKUkXpWm90ukiSO9rJqXrw46TnlWRZ+I8SRdJWiBpwfr164tYdTMzy6fYB8dHRMRqJfPfPyzphZ3kzTepWr2/tUfEJJIZLhk6dKj/9m5WgK1bt1JVVcWWLVsaz2zvG6WlpZSVlVFSUtKi5RY1cETE6vR+naSZJENPayX1jog1Si7YU3OJ0Sp2nC2zjB1nEjWzJqqqqqJ79+7069cPtbNrAllxRAQbN26kqqqK/v37t2jZRRuqSmeZ7F6zTHKVr0Ukk3+NS7ONI7kYDWn6GCWX2+xPMonbvGLVz6wz2bJlC/vuu6+DRiciiX333bcovcxi9jh6kVyMpWY/d0fEXyTNB2ZIuoBkJsozASLiOUkzSGbo3AZ8LZ210sxagING51Os17xogSMi/klyneW66RtJrgWcb5sJJFNnm5lZO9Wh/zluZk3zxbHn88qadY1nLFCf3vtz912NX1Ji5syZnH766Tz//PMMHDiwxfaf60c/+hFXXXVV4xnruPDCC/n2t7/NoEGDGszzy1/+kt12242xY8c2p4r1zJ49mxtvvJEHH3ywwTyVlZWsXr2ak08+uUX33RQdOnAsX76CYz95SoPrC30zm3U2r6xZxwU33Ndi5d15xWkF5Zs6dSojR45k2rRpXHvttfXWV1dX07Vr8/7321DgiAgigi5d8h/aveOOOxot+6tf/Wqz6tYclZWVLFiwoF0Ejg49yeF7W7dxwQ33NXhryV9UZtY8mzdv5oknnuDOO+9k2rRptemzZ89m1KhRfPGLX+Swww6jurqayy+/nCOPPJLy8nJ+9atf1W5//PHHM2TIEA477DDuv//+evsYP34877zzDhUVFZxzzjmsWLGCQw45hEsuuYQhQ4awatUqLr74YoYOHcqhhx7KD37wg9ptjzvuuNopjPbYYw+uvvpqDj/8cIYPH87atWsBuPbaa7nxxhtr83/3u99l2LBhfOQjH+Hxxx8H4O233+YLX/gC5eXlnHXWWRx11FF5p0b6y1/+wsCBAxk5ciT33ntvbfq8efM4+uijOeKIIzj66KNZsmQJ7733Ht///veZPn06FRUVTJ8+PW++1tKhA4eZdRz33XcfJ510Eh/5yEfYZ599ePrp7Vc4njdvHhMmTGDx4sXceeed9OjRg/nz5zN//nxuv/12li9fTmlpKTNnzuTpp5/m0Ucf5bLLLqPuFUwnTpzIrrvuSmVlJb///e8BWLJkCWPHjuWZZ56hb9++TJgwgQULFrBw4UIee+wxFi5cWK+ub731FsOHD+fZZ5/lmGOO4fbbb8/7nLZt28a8efO4+eab+eEPfwjArbfeyt57783ChQu55ppreOqpp+ptt2XLFr7yla/wpz/9iccff5xXX321dt3AgQOZM2cOzzzzDNdddx1XXXUV3bp147rrruOss86isrKSs846K2++1tKhh6rMrOOYOnUql156KQBjxoxh6tSpDBkyBIBhw4bV/tfgoYceYuHChdxzzz0AbNq0iZdeeomysjKuuuoq5syZQ5cuXXjllVdYu3YtBxxwwE7327dvX4YPH177eMaMGUyaNIlt27axZs0aFi9eTHl5+Q7bdOvWjVNOSYbBP/axj/Hwww/nLfv000+vzbNixQoA5s6dy7e+9S0ABg8eXK9sgBdeeIH+/fszYMAAAM4991wmTZpU+3zHjRvHSy+9hCS2bt2ad9+F5isGBw4zK7qNGzfyyCOPsGjRIiRRXV2NJG644QYAdt9999q8EcEtt9zCiSeeuEMZkydPZv369Tz11FOUlJTQr1+/gv6jkFv28uXLufHGG5k/fz5777035513Xt4ySkpKak9l7dq1K9u2bctb9i677FIvT91eUEMaOlX2mmuuYdSoUcycOZMVK1Zw3HHHNStfMXioysyK7p577mHs2LGsXLmSFStWsGrVKvr378/cuXPr5T3xxBO57bbban9Bv/jii7z11lts2rSJ/fffn5KSEh599FFWrsw/M3hJSUmDv77feOMNdt99d3r06MHatWv585//3HJPMjVy5EhmzJgBwOLFi/nHP/5RL8/AgQNZvnw5y5YtA5LeWI1NmzbRp08yTd/kyZNr07t3786bb77ZaL7W4B6HWSfUp/f+BZ8JVWh5OzN16lTGjx+/Q9rnP/957r77bs4666wd0i+88EJWrFjBkCFDiAj2228/7rvvPs455xxOPfVUhg4dSkVFRYOn81500UWUl5czZMgQJkzY8W9hhx9+OEcccQSHHnooBx98MCNGjGjCs925Sy65hHHjxlFeXs4RRxxBeXk5PXr02CFPaWkpkyZN4jOf+Qw9e/Zk5MiRLFq0CIArrriCcePGcdNNN/GJT3yidptRo0YxceJEKioquPLKKxvM1xpUaLeqPeq+517xi8c2NLj+zitO47GHGz4vuiX4Qk7WETz//PMccsghbV2NTqG6upqtW7dSWlrKsmXLOP7443nxxRfp1q1bm9Qn32sv6amcayRl5h6HmVkLevvttxk1ahRbt24lIrjtttvaLGgUiwOHmVkL6t69e5tf0rrYfHDczMwyceAwM7NMHDjMzCwTBw4zM8vEgcPMWsXrr7/OrbfeCiQTG9ZM6dGSzjvvvNqpSgqxYsUKBg8enHdd7qSHtiMHDjNrFbmBo1DV1b4IaHvkwGFmrWL8+PEsW7aMiooKLr/8cjZv3swZZ5zBwIEDOeecc2rneOrXrx/XXXcdI0eO5A9/+AMPPfQQH//4xxkyZAhnnnkmmzdvri1v0KBBlJeX853vfKd2P3PmzOHoo4/m4IMPru19RASXX345gwcP5rDDDmP69On16vfOO+8wZsyY2unQ33nnnVZolY7J/+Mw62QWXnopmyqfbdEye1QcTvnNN+80z8SJE1m0aBGVlZXMnj2b0aNH89xzz3HggQcyYsQInnjiCUaOHAkkU3LMnTuXDRs2cPrpp/PXv/6V3XffnR//+MfcdNNNfP3rX2fmzJm88MILSOL111+v3c+aNWuYO3cuL7zwAp/97Gc544wzuPfee6msrOTZZ59lw4YNHHnkkRxzzDE71O+2225jt912Y+HChSxcuLB25l6rzz0OM2sTw4YNo6ysjC5dulBRUVE7LTlQO3/Vk08+yeLFixkxYgQVFRVMmTKFlStXsueee1JaWsqFF17Ivffey2677Va77WmnnUaXLl0YNGhQ7QWY5s6dy9lnn03Xrl3p1asXxx57LPPnz9+hPnPmzOHcc88FoLy8PO906JZwj8Osk2msZ9BaaqYkh/pTl9dMhR4RfPKTn9xh9tga8+bNY9asWUybNo2f//znPPLII/XKrRn+au5U57Yj9zjMrFXUnRa8EMOHD+eJJ55g6dKlQDIP1IsvvsjmzZvZtGkTJ598MjfffDOVlZU7LeeYY45h+vTpVFdXs379eubMmcOwYcPq5am5auCiRYvyXhnQEu5xmFmr2HfffRkxYgSDBw9m1113pVevXo1us99++zF58mTOPvts3n33XQCuv/56unfvzujRo9myZQsRwU9/+tOdlvO5z32Ov/3tbxx++OG1F5A64IADdhgeu/jii/nyl79MeXk5FRUV9QKLbedp1ZvJ06pbR+Bp1TuvYkyr7qEqMzPLxIHDzMwyceAw6yQ68rC0NU2xXnMHDrNOoLS0lI0bNzp4dCIRwcaNGyktLW3xsn1WlVknUFZWRlVVFevXr2/rqlgrKi0tpaysrMXLdeAw6wRKSkro379/W1fD3ic8VGVmZpk4cJiZWSYOHGZmlokDh5mZZVL0wCGpq6RnJD2YPt5H0sOSXkrv987Je6WkpZKWSDqx2HUzM7PsWqPH8S3g+ZzH44FZETEAmJU+RtIgYAxwKHAScKukrq1QPzMzy6CogUNSGfAZ4I6c5NHAlHR5CnBaTvq0iHg3IpYDSwFPT2lm1s4Uu8dxM3AF8D85ab0iYg1Aer9/mt4HWJWTrypN24GkiyQtkLRg69b3ilJpMzNrWNECh6RTgHUR8VShm+RJqzc/QkRMioihETG0pKRbs+poZmbZFfOf4yOAz0o6GSgF9pT0O2CtpN4RsUZSb2Bdmr8KOChn+zJgdRHrZ2ZmTVC0HkdEXBkRZRHRj+Sg9yMRcS7wADAuzTYOuD9dfgAYI2kXSf2BAcC8YtXPzMyapi3mqpoIzJB0AfAycCZARDwnaQawGNgGfC0iqtugfmZmthOtEjgiYjYwO13eCBzfQL4JwITWqJOZmTWN/zluZmaZOHCYmVkmDhxmZpaJA4eZmWXiwGFmZpk4cJiZWSYOHGZmlokDh5mZZeLAYWZmmThwmJlZJg4cZmaWiQOHmZll4sBhZmaZOHCYmVkmDhxmZpaJA4eZmWXiwGFmZpk4cJiZWSYOHGZmlokDh5mZZeLAYWZmmThwmJlZJg4cZmaWiQOHmZll4sBhZmaZOHCYmVkmDhxmZpaJA4eZmWXiwGFmZpk4cJiZWSYOHGZmlokDh5mZZeLAYWZmmThwmJlZJkULHJJKJc2T9Kyk5yT9ME3fR9LDkl5K7/fO2eZKSUslLZF0YrHqZmZmTVfMHse7wCci4nCgAjhJ0nBgPDArIgYAs9LHSBoEjAEOBU4CbpXUtYj1MzOzJiha4IjE5vRhSXoLYDQwJU2fApyWLo8GpkXEuxGxHFgKDCtW/czMrGmKeoxDUldJlcA64OGI+DvQKyLWAKT3+6fZ+wCrcjavStPqlnmRpAWSFmzd+l4xq29mZnkUNXBERHVEVABlwDBJg3eSXfmKyFPmpIgYGhFDS0q6tVBNzcysUK1yVlVEvA7MJjl2sVZSb4D0fl2arQo4KGezMmB1a9TPzMwKV8yzqvaTtFe6vCtwAvAC8AAwLs02Drg/XX4AGCNpF0n9gQHAvGLVz8zMmuYDRSy7NzAlPTOqCzAjIh6U9DdghqQLgJeBMwEi4jlJM4DFwDbgaxFRXcT6mZlZExQtcETEQuCIPOkbgeMb2GYCMKFYdTIzs+bzP8fNzCwTBw4zM8ukoMAhaVYhaWZm9v6302MckkqB3YCe6ZxSNf+12BM4sMh1MzOzdqixg+P/DlxKEiSeYnvgeAP4RfGqZWZm7dVOA0dE/Az4maRvRMQtrVQnMzNrxwo6HTcibpF0NNAvd5uIuKtI9TIzs3aqoMAh6bfAh4BKoOZPeQE4cJiZdTKF/gFwKDAoIupNOmhmZp1Lof/jWAQcUMyKmJlZx1Boj6MnsFjSPJIr+wEQEZ8tSq3MzKzdKjRwXFvMSpiZWcdR6FlVjxW7ImZm1jEUelbVm2y/Gl83kuuHvxURexarYmZm1j4V2uPonvtY0mnAsGJUyMzM2rcmzY4bEfcBn2jZqpiZWUdQ6FDV6TkPu5D8r8P/6TAz64QKPavq1JzlbcAKYHSL18bMzNq9Qo9xfLnYFTEzs46h0As5lUmaKWmdpLWS/iiprNiVMzOz9qfQg+O/AR4guS5HH+BPaZqZmXUyhQaO/SLiNxGxLb1NBvYrYr3MzKydKjRwbJB0rqSu6e1cYGMxK2ZmZu1ToYHjfOALwKvAGuAMwAfMzcw6oUJPx/0PYFxEvAYgaR/gRpKAYmZmnUihPY7ymqABEBH/Ao4oTpXMzKw9KzRwdJG0d82DtMdRaG/FzMzeRwr98v8J8N+S7iGZauQLwISi1crMzNqtQv85fpekBSQTGwo4PSIWF7VmZmbWLhU83JQGCgcLM7NOrknTqpuZWeflwGFmZpk4cJiZWSZFCxySDpL0qKTnJT0n6Vtp+j6SHpb0Unqfe5rvlZKWSloi6cRi1c3MzJqumD2ObcBlEXEIMBz4mqRBwHhgVkQMAGalj0nXjQEOBU4CbpXUtYj1MzOzJiha4IiINRHxdLr8JvA8yZTso4EpabYpwGnp8mhgWkS8GxHLgaXAsGLVz8zMmqZVjnFI6kcyRcnfgV4RsQaS4ALsn2brA6zK2awqTatb1kWSFkhasHXre0Wtt5mZ1Vf0wCFpD+CPwKUR8cbOsuZJi3oJEZMiYmhEDC0p6dZS1TQzswIVNXBIKiEJGr+PiHvT5LWSeqfrewPr0vQq4KCczcuA1cWsn5mZZVfMs6oE3Ak8HxE35ax6ABiXLo8D7s9JHyNpF0n9gQHAvGLVz8zMmqaYM9yOAL4E/ENSZZp2FTARmCHpAuBl4EyAiHhO0gySaU22AV+LiOoi1s/MzJqgaIEjIuaS/7gFwPENbDMBz7prZtau+Z/jZmaWiQOHmZll4sBhZmaZOHCYmVkmDhxmZpaJA4eZmWXiwGFmZpk4cJiZWSYOHGZmlokDh5mZZeLAYWZmmThwmJlZJg4cZmaWiQOHmZll4sBhZmaZOHCYmVkmDhxmZpaJA4eZmWXiwGFmZpk4cJiZWSYOHGZmlokDh5mZZeLAYWZmmThwmJlZJg4cZmaWiQOHmZll4sBhZmaZOHCYmVkmDhxmZpaJA4eZmWXiwGFmZpk4cJiZWSYOHGZmlokDh5mZZVK0wCHp15LWSVqUk7aPpIclvZTe752z7kpJSyUtkXRiseplZmbNU8wex2TgpDpp44FZETEAmJU+RtIgYAxwaLrNrZK6FrFuZmbWREULHBExB/hXneTRwJR0eQpwWk76tIh4NyKWA0uBYcWqm5mZNV1rH+PoFRFrANL7/dP0PsCqnHxVaVo9ki6StEDSgq1b3ytqZc3MrL4PtHUFUsqTFvkyRsQkYBJA9z33ypunxrJlyzj2k6c0uL5P7/25+65fZ6immZm1duBYK6l3RKyR1BtYl6ZXAQfl5CsDVjd3Z9UBF9xwX4Pr77zitObuwsys02ntoaoHgHHp8jjg/pz0MZJ2kdQfGADMa+W6mZlZAYrW45A0FTgO6CmpCvgBMBGYIekC4GXgTICIeE7SDGAxsA34WkRUF6tuZmbWdEULHBFxdgOrjm8g/wRgQrHqY2ZmLcP/HDczs0wcOMzMLBMHDjMzy8SBw8zMMnHgMDOzTBw4zMwsEwcOMzPLxIHDzMwyceAwM7NMHDjMzCyT9jKtepvwtOtmZtl16sDhadfNzLLzUJWZmWXiwGFmZpk4cJiZWSYOHGZmlokDh5mZZeLAYWZmmThwmJlZJg4cZmaWiQOHmZll4sBhZmaZOHCYmVkmDhxmZpZJp57ksDGFzJ57cSvWx8ysPXDg2AnPnmtmVp8DRzMsW7aMytfWA/C9BnomvqaHmb3fOHA0Q3XAAR8aDDTcM7nq84f5YlFm9r7iwFFkHu4ys/cbn1VlZmaZOHCYmVkmHqrq4L449nxeWbOuwfU+hmJmLc2Bo4N7Zc06H0Mxs1blwNHGGvuT4erVVRx4YFmD65evXFmManUa7rGZZdfuAoekk4CfAV2BOyJiYhtXqagaO+vqu6cf1uj65mjsi7OxwNXY+uZ+8Rb7i909NrPs2lXgkNQV+AXwSaAKmC/pgYhY3LY167ga69EsX7mS66c/0+D6QgJXc754GwsMjdXPX+y2M429v6D9/7hpj9pV4ACGAUsj4p8AkqYBowEHjiYqpEdTTC0RuJpTfnOH+ppbfkdf39iXXnvvsTbWo4Tm//hobB/F/hNwWwQuRUSLFtgcks4AToqIC9PHXwKOioiv5+S5CLgofTgYWNTqFW2fegIb2roS7YTbYju3xXZui+0+GhHdm7pxe+txKE/aDpEtIiYBkwAkLYiIoa1RsfbObbGd22I7t8V2bovtJC1ozvbt7Q+AVcBBOY/LgNVtVBczM8ujvQWO+cAASf0ldQPGAA+0cZ3MzCxHuxqqiohtkr4O/BfJ6bi/jojndrLJpNapWYfgttjObbGd22I7t8V2zWqLdnVw3MzM2r/2NlRlZmbtnAOHmZll0mEDh6STJC2RtFTS+LauT7FJ+rWkdZIW5aTtI+lhSS+l93vnrLsybZslkk5sm1q3PEkHSXpU0vOSnpP0rTS9M7ZFqaR5kp5N2+KHaXqna4sakrpKekbSg+njTtkWklZI+oekyppTb1u0LSKiw91IDpwvAw4GugHPAoPaul5Ffs7HAEOARTlpNwDj0+XxwI/T5UFpm+wC9E/bqmtbP4cWaofewJB0uTvwYvp8O2NbCNgjXS4B/g4M74xtkdMm3wbuBh5MH3fKtgBWAD3rpLVYW3TUHkft1CQR8R5QMzXJ+1ZEzAH+VSd5NDAlXZ4CnJaTPi0i3o2I5cBSkjbr8CJiTUQ8nS6/CTwP9KFztkVExOb0YUl6CzphWwBIKgM+A9yRk9wp26IBLdYWHTVw9AFW5TyuStM6m14RsQaSL1Rg/zS9U7SPpH7AESS/tDtlW6RDM5XAOuDhiOi0bQHcDFwB/E9OWmdtiwAekvRUOk0TtGBbtKv/cWTQ6NQkndz7vn0k7QH8Ebg0It6Q8j3lJGuetPdNW0RENVAhaS9gpqTBO8n+vm0LSacA6yLiKUnHFbJJnrT3RVukRkTEakn7Aw9LemEneTO3RUftcXhqksRaSb0B0vuaKTLf1+0jqYQkaPw+Iu5NkztlW9SIiNeB2cBJdM62GAF8VtIKkqHrT0j6HZ2zLYiI1en9OmAmydBTi7VFRw0cnpok8QAwLl0eB9yfkz5G0i6S+gMDgHltUL8Wp6RrcSfwfETclLOqM7bFfmlPA0m7AicAL9AJ2yIiroyIsojoR/J98EhEnEsnbAtJu0vqXrMMfIpkFvGWa4u2PvrfjLMGTiY5o2YZcHVb16cVnu9UYA2wleQXwgXAvsAs4KX0fp+c/FenbbME+HRb178F22EkSTd6IVCZ3k7upG1RDjyTtsUi4Ptpeqdrizrtchzbz6rqdG1Bcrbps+ntuZrvx5ZsC085YmZmmXTUoSozM2sjDhxmZpaJA4eZmWXiwGFmZpk4cJiZWSYOHGZmlokDh1kLk9S1retgVkwOHGYZSbovnTzuuZoJ5CRtlnSdpL8DH5d0bnqtjEpJv6oJJpJuk7Qg9/oZZh2NA4dZdudHxMeAocA3Je0L7E5yrZSjgI3AWSQTzVUA1cA56bZXR8RQkn99HyupvNVrb9ZMHXV2XLO29E1Jn0uXDyKZ26eaZOJFgOOBjwHz01l7d2X7hHJfSHspHyC5KNUgkilDzDoMBw6zDNIpu08APh4Rb0uaDZQCWyKZ4hySaaqnRMSVdbbtD3wHODIiXpM0Od3WrEPxUJVZNj2A19KgMZDkUq11zQLOSK+FUHOt577AnsBbwCZJvYBPt1alzVqSexxm2fwF+KqkhSQziT5ZN0NELJb0PZIrsHUhmdH4axHxpKRnSGYs/SfwRCvW26zFeHZcMzPLxENVZmaWiQOHmZll4sBhZmaZOHCYmVkmDhxmZpaJA4eZmWXiwGFmZpn8fyWRkLehXeT3AAAAAElFTkSuQmCC\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, axis = plt.subplots()\n",
+    "\n",
+    "axis.hist(area, label='Area training data', bins = 500, alpha=0.7, color = '#79bafa', edgecolor='black', range = (0,6000))\n",
+    "axis.set_xlim(0,500)\n",
+    "axis.axvline(threshold, color = '#ae0001', label = 'threshold')\n",
+    "axis.set_xlabel('area')\n",
+    "axis.set_ylabel('count')\n",
+    "axis.legend()\n",
+    "axis.set_title('Distribution of labels before small label exclusion')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "72c83cf2-fbcb-4242-ba5a-d0f35e38ab66",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[0, 0, 0, 0, 0]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "area_threshold = 50\n",
+    "thresholded_groups = [0 if area < 50 else 1 for area in regprops[\"area_norm\"]]\n",
+    "thresholded_groups[:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "03d44312-b311-4165-aceb-7d5b7b454c17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "regprops[\"thresholded_groups\"] = thresholded_groups"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "fe500edc-0b2e-4cd9-9cd0-5a5ee0a47fe2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from napari_clusters_plotter._utilities import get_nice_colormap\n",
+    "\n",
+    "colormap_dict = {i: color for i,color in enumerate(get_nice_colormap())}"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
+%% Cell type:markdown id:15fee2ed-980b-4d1a-a31a-1e261c31d9aa tags:
+
+# Figure 5.06: Small label exclusion
+
+%% Cell type:code id:39cd2c59-0e87-4083-8158-c8b4307a7126 tags:
+
+``` python
+import pandas as pd
+import seaborn as sns
+import matplotlib as mpl
+import matplotlib.pyplot as plt
+```
+
+%% Cell type:code id:3dcc5326-9284-4da5-90eb-69ae42bb4ad6 tags:
+
+``` python
+all_labels_training = pd.read_csv("Measurements_with_frame_clustering_with_GMM.csv")
+```
+
+%% Cell type:code id:0abc6b00-0cec-4a92-a30c-d97ae5094af2 tags:
+
+``` python
+area = all_labels_training['area_norm']
+```
+
+%% Cell type:code id:aa69fed7-a1f4-48df-9f8e-31a5207dbfb8 tags:
+
+``` python
+threshold = 50
+```
+
+%% Cell type:code id:1284e287-6ac8-4cf6-93cf-7fa8eeed6fd0 tags:
+
+``` python
+fig, axis = plt.subplots()
+
+axis.hist(area, label='Area training data', bins = 500, alpha=0.7, color = '#79bafa', edgecolor='black', range = (0,6000))
+axis.set_xlim(0,500)
+axis.axvline(threshold, color = '#ae0001', label = 'threshold')
+axis.set_xlabel('area')
+axis.set_ylabel('count')
+axis.legend()
+axis.set_title('Distribution of labels before small label exclusion')
+```
+
+%% Output
+
+    Text(0.5, 1.0, 'Distribution of labels before small label exclusion')
+
+
+
+%% Cell type:code id:72c83cf2-fbcb-4242-ba5a-d0f35e38ab66 tags:
+
+``` python
+area_threshold = 50
+thresholded_groups = [0 if area < 50 else 1 for area in regprops["area_norm"]]
+thresholded_groups[:5]
+```
+
+%% Output
+
+    [0, 0, 0, 0, 0]
+
+%% Cell type:code id:03d44312-b311-4165-aceb-7d5b7b454c17 tags:
+
+``` python
+regprops["thresholded_groups"] = thresholded_groups
+```
+
+%% Cell type:code id:fe500edc-0b2e-4cd9-9cd0-5a5ee0a47fe2 tags:
+
+``` python
+from napari_clusters_plotter._utilities import get_nice_colormap
+
+colormap_dict = {i: color for i,color in enumerate(get_nice_colormap())}
+```
--- a/plots/Figure_4.05_and_Figure_4.09_segmentation_gt_classification.ipynb
+++ b/plots/Figure_4.05_and_Figure_4.09_segmentation_gt_classification.ipynb
--- a/plots/Figure_4.10_Jaccard_index.ipynb
+++ b/plots/Figure_4.10_Jaccard_index.ipynb
--- a/plots/Figure_5.14_and_Figure_5.15_Plotting_area_with_shape_classifier.ipynb
+++ b/plots/Figure_5.14_and_Figure_5.15_Plotting_area_with_shape_classifier.ipynb
--- a/plots/Figure_5.17 - Figure_5.20_Plotting_shape.ipynb
+++ b/plots/Figure_5.17 - Figure_5.20_Plotting_shape.ipynb
--- a/plots/Figure_5.19_Solidity comparison with initial data.ipynb
+++ b/plots/Figure_5.19_Solidity comparison with initial data.ipynb
--- a/plots/Figure_5.21_Scatterplots.ipynb
+++ b/plots/Figure_5.21_Scatterplots.ipynb
--- a/plots/Figure_6.03_Solidity results of different classifiers compared.ipynb
+++ b/plots/Figure_6.03_Solidity results of different classifiers compared.ipynb